Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling

• URL: http://arxiv.org/abs/2510.04087v2
• Date: Fri, 10 Oct 2025 21:47:22 GMT
• Title: Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling
• Authors: Hyung Gyu Rho, Sian Lee,
• Abstract summary: Modern preference alignment techniques, such as Best-of-N sampling, rely on reward models trained with pairwise comparison data.<n>We introduce a new data collection and modeling framework to address this critical reliability gap.<n>We show that when tuned as an alignment guardrail, it reduces reliability failures by 70%, and when tuned as an inference accelerator, it improves average inference speed by over 22%.
• Score: 0.14323566945483493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern preference alignment techniques, such as Best-of-N (BoN) sampling, rely on reward models trained with pairwise comparison data. While effective at learning relative preferences, this paradigm fails to capture a signal of response acceptability, leaving systems vulnerable to selecting the least bad of many unacceptable options. This is particularly problematic for hard prompts, where the risk of such false acceptances increases with the number of samples. In this paper, we address this critical reliability gap by introducing a new data collection and modeling framework. By augmenting preference data with an outside option, inspired by discrete choice models, we train a reward model that can distinguish not just what is better, but what is good enough. We leverage this capability to create an adaptive inference strategy, best of mini-N in-loop, which partitions the generation budget into sequential loops with a calibrated, early-exit condition. Our experiments show that when tuned as an alignment guardrail, it reduces reliability failures by 70%, and when tuned as an inference accelerator, it improves average inference speed by over 22% in IMDB-sentiment setting. We thus provide a principled and flexible framework for practitioners to explicitly manage the trade-off between reliability and computational efficiency.

Related papers

• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models [2.4065240342323384]
  This paper introduces Efficient Adaptive Rejection Sampling (EARS)<n>EARS dynamically adjusts the acceptance threshold by incorporating the target model's own predictive uncertainty, measured as 1 - max(P_target)<n>It significantly enhances the efficiency of speculative decoding, achieving up to an 18.12% increase in throughput with a negligible 0.84% accuracy drop on the GSM8K benchmark.
  arXiv  Detail & Related papers  (2025-12-15T11:08:56Z)
• Robust Preference Alignment via Directional Neighborhood Consensus [13.313830197011983]
  We introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus.<n>RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool.<n>Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models.
  arXiv  Detail & Related papers  (2025-10-23T12:39:20Z)
• LLM Routing with Dueling Feedback [49.67815163970033]
  We study the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost.<n>We formulate routing as contextual dueling bandits, learning from pairwise preference feedback rather than absolute scores.<n>We introduce Category-Calibrated Fine-Tuning (CCFT), a representation-learning method that derives model embeddings from offline data using contrastive fine-tuning with categorical weighting.
  arXiv  Detail & Related papers  (2025-10-01T12:52:25Z)
• More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment [80.04449725137177]
  Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback.<n>Our study reveals a striking, safety-specific phenomenon associated with DPO alignment.<n>Using solely self-generated responses for both chosen and rejected pairs significantly outperforms configurations that incorporate responses from stronger models.
  arXiv  Detail & Related papers  (2025-04-03T00:36:40Z)
• Optimizing Asynchronous Federated Learning: A~Delicate Trade-Off Between Model-Parameter Staleness and Update Frequency [0.9999629695552195]
  We use modeling and analysis to better understand the impact of design choices in asynchronous FL algorithms.<n>We characterize a fundamental trade-off for optimizing asynchronous FL.<n>We show that these optimizations enhance accuracy by 10% to 30%.
  arXiv  Detail & Related papers  (2025-02-12T08:38:13Z)
• Calibrated Multi-Preference Optimization for Aligning Diffusion Models [90.15024547673785]
  Calibrated Preference Optimization (CaPO) is a novel method to align text-to-image (T2I) diffusion models.<n>CaPO incorporates the general preference from multiple reward models without human annotated data.<n> Experimental results show that CaPO consistently outperforms prior methods.
  arXiv  Detail & Related papers  (2025-02-04T18:59:23Z)
• InfAlign: Inference-aware language model alignment [58.66389179049758]
  Language model alignment is a critical step in training modern generative language models.<n>We show that this train/test mismatch makes standard RLHF framework sub-optimal in view of inference-time methods.<n>We propose a framework for inference-aware alignment (InfAlign), which aims to optimize inference-time win rate of the aligned policy against the base model.
  arXiv  Detail & Related papers  (2024-12-27T18:45:36Z)
• Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization [9.618391485742968]
  Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs) We present an uncertainty-enhanced textbfPreference textbfOptimization framework to make the LLM self-evolve with reliable feedback. Our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization.
  arXiv  Detail & Related papers  (2024-09-17T14:05:58Z)
• Adversarial Robustification via Text-to-Image Diffusion Models [56.37291240867549]
  Adrial robustness has been conventionally believed as a challenging property to encode for neural networks. We develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data.
  arXiv  Detail & Related papers  (2024-07-26T10:49:14Z)
• BOND: Aligning LLMs with Best-of-N Distillation [63.254031574394965]
  We propose Best-of-N Distillation (BOND), a novel RLHF algorithm that seeks to emulate Best-of-N but without its significant computational overhead at inference time. Specifically, BOND is a distribution matching algorithm that forces the distribution of generations from the policy to get closer to the Best-of-N distribution. We demonstrate the effectiveness of our approach and several design choices through experiments on abstractive summarization and Gemma models.
  arXiv  Detail & Related papers  (2024-07-19T18:38:25Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding [38.11411155621616]
  We study self-training as one of the predominant semi-supervised learning approaches. We present UPET, a novel Uncertainty-aware self-Training framework. We show that UPET achieves a substantial improvement in terms of performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-19T02:18:29Z)
• Contrastive Neural Ratio Estimation for Simulation-based Inference [15.354874711988662]
  Likelihood-to-evidence ratio estimation is usually cast as either a binary (NRE-A) or a multiclass (NRE-B) classification task. In contrast to the binary classification framework, the current formulation of the multiclass version has an intrinsic and unknown bias term. We propose a multiclass framework free from the bias inherent to NRE-B at optimum, leaving us in the position to run diagnostics that practitioners depend on.
  arXiv  Detail & Related papers  (2022-10-11T00:12:51Z)
• Error-based Knockoffs Inference for Controlled Feature Selection [49.99321384855201]
  We propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together. The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees.
  arXiv  Detail & Related papers  (2022-03-09T01:55:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.